• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.712-717
• /
• 2007

Using home network system including home server, home service robot, a variety of device, it is generally known that application of Multi Agent System for performing variously distributed process that can be occur in home environment, is efficient method. In this system, it is intelligent service robot that a key of human interface and physical service offer Therefore, using application of established multi agent system, we can defined Multi Agent Robot System. In 'open' home environment, between all agent data interaction and cooperation are needed for Multi Agent System offer to user that more efficient service. For this, we focus our attention on define as agent that can autonomic drive and offer to user that physical service robots and, design, suggest the simulator can display that between robot agents communication or between other agents, like home server, and robot agents communication information to user interface.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.3
• /
• pp.125-134
• /
• 2014

This paper proposes a multi-agent message transport architecture to support application areas which need fast message communications for close collaboration among agents. In the FIPA(Foundation of Intelligent Physical Agents) agent platform, all message transfer services among agents are in charge of a conceptual entity named ACC(Agent Communication Channel). In our multi-agent message transport architecture, the ACC is represented as a set of system agents named MTSA(Message Transfer Service Agent). The MTSA enables close collaboration among agents by supporting asynchronous communication, by using Reactor pattern to handle agent input messages efficiently, and by selecting optimal message transfer protocols according to the relative positional relationships of sender agents and receiver agents. The multi-agent framework SMAF(Small Multi-Agent Framework), which is implemented on the proposed multi-agent message transport architecture, shows better performance on message transfer among agents than JADE(Java Agent Development Environment) which is a well-known FIPA-compliant multi-agent framework. The faster the speed of message transfer of a multi-agent architecture becomes, the wider application areas the architecture can support.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1004-1012
• /
• 2021

The collaboration productively interacting between multi-agents has become an emerging issue in real-world applications. In reinforcement learning, multi-agent environments present challenges beyond tractable issues in single-agent settings. This collaborative environment has the following highly complex attributes: sparse rewards for task completion, limited communications between each other, and only partial observations. In particular, adjustments in an agent's action policy result in a nonstationary environment from the other agent's perspective, which causes high variance in the learned policies and prevents the direct use of reinforcement learning approaches. Unexpected social loafing caused by high dispersion makes it difficult for all agents to succeed in collaborative tasks. Therefore, we address a paradox caused by the social loafing to significantly reduce total returns after a certain timestep of multi-agent reinforcement learning. We further demonstrate that the collaborative paradox in multi-agent environments can be avoided by our proposed effective early stop method leveraging a metric for social loafing.

• The Journal of Korea Robotics Society
• /
• v.1 no.1
• /
• pp.46-57
• /
• 2006

It is well known that mathematical solutions for multi-agent planning problems are very difficult to obtain due to the complexity of mutual interactions among multi-agent. Most of the past research results thus are based on the probabilistic completeness. However, the practicality and effectiveness of the solution from the probabilistic completeness is significantly reduced by heavy computational burden. In this paper, we propose a practically applicable solution technique for multi-agent planning problems, which assures a reasonable computation time and a real world application for more than 3 multi-agents for the case of general shaped paths in agent movement. First, to reduce the computation time, a collision map is utilized for detecting potential collisions and obtaining collision-free solutions for multi-agents. Second, to minimize the maximum of multi-agent task execution time, a method is developed for selecting an optimal priority order. Simulations are finally provided for more than 20 agents to emphasize the effectiveness of the proposed interactive approach to multi-agent planning problems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.3
• /
• pp.1321-1332
• /
• 2016

Wireless sensor networks (WSN) are self-organized networks that typically consist of thousands of low-cost, low-powered sensor nodes. The reliability and availability of WSNs can be affected by faults, including those from radio interference, battery exhaustion, hardware and software failures, communication link errors, malicious attacks, and so on. Thus, we propose a novel multi-agent fault tolerant system for wireless sensor networks. Since a major requirement of WSNs is to reduce energy consumption, we use multi-agent and mobile agent configurations to manage WSNs that provide energy-efficient services. Mobile agent architecture have inherent advantages in that they provide energy awareness, scalability, reliability, and extensibility. Our multi-agent system consists of a resource manager, a fault tolerance manager and a load balancing manager, and we also propose fault-tolerant protocols that use multi-agent and mobile agent setups.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2003.05a
• /
• pp.1-20
• /
• 2003

In this research, we developed a Multi-Agent based Negotiation Support System to be able to increase the competitive power of a company in dynamic environment and correspond to various orders of customers by diffusion of electronic commerce. The system uses the agent technology that is being embossed as new paradigm in dynamic environment and flexible system framework. The multi-agent technology is used to solve these problem through cooperation of agent. The system consists of six sub agents: mediator, manufacturability analysis agent, process planning agent, scheduling agent, selection agent, negotiation-strategy building agent. In this paper, the proposed Multi-Agent based Negotiation Support System takes aim at the automation of transaction process from ordering to manufacturing plan through the automation of negotiation that is the most important in order-taking transaction.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.4
• /
• pp.537-542
• /
• 2008

The protection against transient instability and consequent out-of-step condition is a major concern for the utility industry. Unstable system may cause serious damage to system elements such as generators and transmission lines. Therefore, out-of-step detection is essential to operate a system safely. Also, a multi-agent system is one that consists of a number of agents, which interact with one another. Multi-agent systems(MAS) can offer the flexibility and the adaptability to the previous algorithm. In this paper, the detection algorithm of out-of-step is designed by multi-agent system and implemented by EMTP-MODELS. To verify performance of the proposed algorithm based on multi-agent system, simulations by EMTP have been carried out.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.118-136
• /
• 1997

The multi-agent system is an environment in which applications solve tasks by cooperating with each other. In the multi-agent system, a user can solve complex problems by issuing a single command instead of a series of commands. However, agents depend on the state of other agents for they cooperate with each other. The problem worsens as multi-agent systems are connected to from a group of multi-agent systems. In this paper, we present the termination problem of an agent in a multi-agent system or a group of multi-agent systems. We also give asolution of the problem and present an example through implemented multi-agent systems.

• Proceedings of the KIEE Conference
• /
• 2008.11a
• /
• pp.6-8
• /
• 2008

본 논문은 전력IT 분야에 새롭게 큰 관심이 집중되고 있는 Multi-Agent System 적용에 대하여 배전자동화 시스템에서의 적용방안을 제안하고 있다. IEEE Working Group에서 Power System에 적용되는 Multi-Agent에 대한 연구를 진행하였다. 이 내용을 기반으로 배 전자동화 시스템에서는 어떻게 Multi-Agent System이 적응되어야 하는지에 대한 방법을 제안하고 있다.

• Korean Journal of Computational Design and Engineering
• /
• v.8 no.1
• /
• pp.55-63
• /
• 2003

ADE i,1 a software tool for the design and implementation of multi-agent systems. ADE allows a designer to draw a multi-agent system graphically, specify the necessary properties, and deploy their applications. ADE offers a set of intuitive, easy to use interfaces that enable a designer to completely specify the agents and agent interactions in a multi-agent system. In this environment, JATLite/sup ［1］/ is improved significantly. Furthermore, ADE provides a unique set of features for a multi-agent system design tool. An agent description method based on Design roadmap/sup ［2］/ theory, a hierarchy of agents, and a fully featured Java-based Graphical User Interface are combined in ADE. This distinct combination of features mates ADE stand out among the existing multi-agent system design tools. This paper presents the research related to the application of the ADE, along with descriptions of its design and implementation.